Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 17:25:07 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/server-self-hosted.yml
#	.github/workflows/ui-build-self-hosted.yml
#	.github/workflows/ui-build.yml
#	.github/workflows/ui.yml
#	ggml/src/ggml-sycl/mmvq.cpp
#	ggml/src/ggml-sycl/vecdotq.hpp
#	tests/test-backend-ops.cpp
#	tests/test-sampling.cpp
#	tools/cli/README.md
#	tools/server/README.md
This commit is contained in:
Concedo
2026-09-09 11:47:23 +08:00
parent b72d1de1ac 304665fe7a
commit ad1eee0c5f
18 changed files with 337 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-context.cpp
+17 -1
View File
@@ -2311,8 +2311,11 @@ private:
// evict checkpoints within min-step of a previous checkpoint, unless they were
// created by the current task
// only when the list is full, otherwise short prompts keep just the oldest checkpoint
int64_t last = -1;
for (auto it = slot.prompt.checkpoints.begin(); it != slot.prompt.checkpoints.end(); ) {
for (auto it = slot.prompt.checkpoints.begin();
slot.prompt.checkpoints.size() + 1 >= (size_t) params_base.n_ctx_checkpoints &&
it != slot.prompt.checkpoints.end(); ) {
if (it->id_task != id_task && last >= 0 && it->n_tokens <= last + params_base.checkpoint_min_step) {
SLT_TRC(slot, "erasing context checkpoint too close to an earlier one (pos_min = %d, pos_max = %d, n_tokens = %" PRId64 ", size = %.3f MiB)\n",
it->pos_min, it->pos_max, it->n_tokens, (float) it->size() / 1024 / 1024);
@@ -2335,6 +2338,19 @@ private:
slot.prompt.checkpoints.erase(slot.prompt.checkpoints.begin());
}
// replace an existing checkpoint at the same n_tokens instead of appending a duplicate
{
const int64_t n_tokens_new = slot.prompt.n_tokens() - n_tokens_cur;
for (auto it = slot.prompt.checkpoints.begin(); it != slot.prompt.checkpoints.end(); ) {
if (it->n_tokens == n_tokens_new) {
SLT_TRC(slot, "superseding context checkpoint at n_tokens = %" PRId64 "\n", it->n_tokens);
it = slot.prompt.checkpoints.erase(it);
} else {
++it;
}
}
}
auto & cur = slot.prompt.checkpoints.emplace_back();
cur.id_task = id_task;